Open-weight model
qwen3-sft-feedback-with-proof-repair-rl-200-unmasked
by Formalmathatepfl formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked
qwen3-sft-feedback-with-proof-repair-rl-200-unmasked is an open-weight model from Formalmathatepfl. It has 8.2B parameters and a 32,768-token context. At 16-bit it needs about 19.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve qwen3-sft-feedback-with-proof-repair-rl-200-unmasked (8.2B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 16.4 GB | 19.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.2 GB | 9.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.1 GB | 4.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen3ForCausalLM
- Context length (tokens)
- 32,768
- Layers
- 36
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 151,936
- RoPE base
- 1,000,000
- Model type
- qwen3
Identity and Version
- Repository
- formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked
- Publisher
- Formalmathatepfl
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 8.2B parameters
- Languages
- Not stated by the source
- Revision
- a6ae0f1c28b8cd6e7d8f1f98a0282610a05d63c5
- First published
- 2026-09-23
- Last updated
- 2026-09-24
Files and Weights
15 files, 16.4 GB in total. The weights are 4 files totalling 16.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 5.0 GB | d64243f9b1e3 |
| model-00002-of-00004.safetensors | Weights | 4.9 GB | c2d992ade330 |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | 13e0f4cad059 |
| model-00004-of-00004.safetensors | Weights | 1.5 GB | 1a422cb7ef1a |
| added_tokens.json | Configuration | 707 B | — |
| config.json | Configuration | 1.5 KB | — |
| generation_config.json | Configuration | 127 B | — |
| model.safetensors.index.json | Configuration | 32.9 KB | — |
| special_tokens_map.json | Configuration | 616 B | — |
| chat_template.jinja | Other | 110 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| tokenizer_config.json | Tokenizer | 5.4 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 16.4 GB
Released by Formalmathatepfl through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 16.4 GB |
| 16-bit | 16.4 GB |
| 8-bit | 8.2 GB |
| 4-bit | 4.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About qwen3-sft-feedback-with-proof-repair-rl-200-unmasked
How much GPU memory does qwen3-sft-feedback-with-proof-repair-rl-200-unmasked need?
About 19.7 GB at 16-bit and 4.9 GB at 4-bit: the weights (8.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run qwen3-sft-feedback-with-proof-repair-rl-200-unmasked on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is qwen3-sft-feedback-with-proof-repair-rl-200-unmasked's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.